Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    LaTeX commands related to mathematical formatting and packages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    start of user input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -1.08
    MessageTagHelper
    -1.04
    adaptiveStyles
    -1.01
    verwijspagina
    -1.00
     queſta
    -0.98
     disambiguazione
    -0.89
     kasarigan
    -0.89
     Administrativna
    -0.86
     autorytatywna
    -0.83
    Derbyniad
    -0.82
    POSITIVE LOGITS
    .
    0.54
     
    0.49
    ,
    0.43
    -
    0.42
     .
    0.40
    /
    0.37
     B
    0.35
     and
    0.35
     to
    0.35
    лин
    0.35
    Act Density 0.001%

    No Known Activations